Department of Radiology, Chongqing University Cancer Hospital, Chongqing, PR China.
Department of Radiology, Chongqing University Cancer Hospital, Chongqing, PR China.
Clin Radiol. 2023 Mar;78(3):e279-e287. doi: 10.1016/j.crad.2022.11.015. Epub 2022 Dec 26.
To evaluate the predictive performance of the radiomics model in predicting axillary lymph node (ALN) metastasis through the associations between radiomics features and genomic features in patients with breast cancer.
Patients with breast cancer were enrolled retrospectively from a public database (111 patients as training group) and one hospital (15 patients as external validation group). The genomics features from transcriptome data and radiomics features from dynamic contrast-enhanced magnetic resonance imaging (MRI) were collected. Firstly, overlapping genes were identified using the Kyoto Encyclopedia of Genes and Genomes and differentially expressed gene analysis, while radiomics features were reduced using a data-driven method. Then, the associations between overlapping genes and retained radiomics features were assessed to obtain key pairs of radiomics-genomics features. Furthermore, the least absolute shrinkage and selection operator (LASSO) algorithm was used to detect the key-pairs features. Finally, radiomics and genomics models were constructed to predict ALN metastasis.
After using the hybrid data- and gene-driven selection method, key pairs of features were detected, which consisted of six radiomic features associated with four genomic features. The radiomics model exhibited comparable performance to the genomics model in predicting ALN metastasis (radiomic model: area under the curve [AUC] = 0.71, sensitivity = 77%, specificity = 56%; genomic model: AUC = 0.72, sensitivity = 85%, specificity = 74%). The four genomic features were enriched in six pathways and related to metabolism and human diseases.
The radiomics model established using the gene-driven hybrid selection method could predict ALN metastasis in breast cancer, which showed comparable performance to the genomics model.
通过乳腺癌患者的影像组学特征与基因组特征之间的关联，评估基于影像组学模型预测腋窝淋巴结（ALN）转移的预测性能。
本研究回顾性地从一个公共数据库（111 例患者作为训练组）和一家医院（15 例患者作为外部验证组）中招募了乳腺癌患者。收集了来自转录组数据的基因组特征和来自动态对比增强磁共振成像（MRI）的影像组学特征。首先，使用京都基因与基因组百科全书和差异表达基因分析来识别重叠基因，同时使用数据驱动的方法来减少影像组学特征。然后，评估重叠基因与保留的影像组学特征之间的关联，以获得影像组学-基因组特征的关键对。此外，使用最小绝对收缩和选择算子（LASSO）算法来检测关键对特征。最后，构建影像组学和基因组模型来预测 ALN 转移。
使用混合数据和基因驱动的选择方法后，检测到了关键特征对，其中包含 6 个与 4 个基因组特征相关的影像组学特征。影像组学模型在预测 ALN 转移方面与基因组模型表现相当（影像组学模型：曲线下面积 [AUC] = 0.71，敏感性 = 77%，特异性 = 56%；基因组模型：AUC = 0.72，敏感性 = 85%，特异性 = 74%）。这四个基因组特征在六个通路中被富集，与代谢和人类疾病相关。
使用基因驱动的混合选择方法建立的影像组学模型可以预测乳腺癌的 ALN 转移，其表现与基因组模型相当。
